Sandesh Kamath

According to our database, Sandesh Kamath authored at least 8 papers between 2020 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Rethinking Robustness of Model Attributions.

Sandesh Kamath, Sankalp Mittal, Amit Deshpande, Vineeth N. Balasubramanian

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2022

On the Robustness of Explanations of Deep Neural Network Models: A Survey.

Amlan Jyoti, Karthik Balaji Ganesh, Manoj Gayala, Nandita Lakshmi Tunuguntla, Sandesh Kamath, Vineeth N. Balasubramanian

CoRR, 2022

Universalization of Any Adversarial Attack using Very Few Test Examples.

Sandesh Kamath, Amit Deshpande, K. V. Subrahmanyam, Vineeth N. Balasubramanian

Proceedings of the CODS-COMAD 2022: 5th Joint International Conference on Data Science & Management of Data (9th ACM IKDD CODS and 27th COMAD), Bangalore, India, January 8, 2022

2021

Can we have it all? On the Trade-off between Spatial and Adversarial Robustness of Neural Networks.

Sandesh Kamath, Amit Deshpande, Subrahmanyam Kambhampati Venkata, Vineeth N. Balasubramanian

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

2020

How do SGD hyperparameters in natural training affect adversarial robustness?

Sandesh Kamath, Amit Deshpande, K. V. Subrahmanyam

CoRR, 2020

On Universalized Adversarial and Invariant Perturbations.

Sandesh Kamath, Amit Deshpande, K. V. Subrahmanyam

CoRR, 2020

Universalization of any adversarial attack using very few test examples.

Sandesh Kamath, Amit Deshpande, K. V. Subrahmanyam

CoRR, 2020

Invariance vs. Robustness of Neural Networks.

Sandesh Kamath, Amit Deshpande, K. V. Subrahmanyam

CoRR, 2020